Benchmarking fixed-length Fingerprint Representations across different Embedding Sizes and Sensor Types

Tim Rohwedder, Daile Osorio-Roig, Christian Rathgeb, Christoph Busch
7/17/2023
cs.CV

No official code found. Best implementation: tim-rohwedder/fixed-length-fingerprint-extractors (45 stars, LGPL-3.0, last commit 2024-01-26).

Abstract

Traditional minutiae-based fingerprint representations consist of a variable-length set of minutiae. This necessitates a more complex comparison causing the drawback of high computational cost in one-to-many comparison. Recently, deep neural networks have been proposed to extract fixed-length embeddings from fingerprints. In this paper, we explore to what extent fingerprint texture information contained in such embeddings can be reduced in terms of dimension while preserving high biometric performance. This is of particular interest since it would allow to reduce the number of operations incurred at comparisons. We also study the impact in terms of recognition performance of the fingerprint textural information for two sensor types, i.e. optical and capacitive. Furthermore, the impact of rotation and translation of fingerprint images on the extraction of fingerprint embeddings is analysed. Experimental results conducted on a publicly available database reveal an optimal embedding size of 512 feature elements for the texture-based embedding part of fixed-length fingerprint representations. In addition, differences in performance between sensor types can be perceived.

View on arXivView PDF

Code Implementations(1)

tim-rohwedder/fixed-length-fingerprint-extractorsCommunity65%
LGPL-3.0

Implementation of Deep Print, a Deep Learning based fixed-length Fingerprint Representation extractor, and various experiments with such architectures. See: https://arxiv.org/abs/2307.08615

4516Python, Jupyter NotebookAug 22, 20232 years agoLGPL-3.0

Similar Papers

Fixed-length Dense Descriptor for Efficient Fingerprint Matching

86% match2023

IFViT: Interpretable Fixed-Length Representation for Fingerprint Matching via Vision Transformer

86% match1 repo132024

Deep Learning-Based Approaches for Contactless Fingerprints Segmentation and Extraction

84% match2023

Enhancing Fingerprint Recognition Systems: Comparative Analysis of Biometric Authentication Algorithms and Techniques for Improved Accuracy and Reliability

82% match2024

Robust Minutiae Extractor: Integrating Deep Networks and Fingerprint Domain Knowledge

82% match1 repo1522017

MRA-GNN: Minutiae Relation-Aware Model over Graph Neural Network for Fingerprint Embedding

82% match2023

Cite this paper

@article{rohwedder2023benchmarking,
  title  = {Benchmarking fixed-length Fingerprint Representations across different Embedding Sizes and Sensor Types},
  author = {Tim Rohwedder and Daile Osorio-Roig and Christian Rathgeb and Christoph Busch},
  year   = {2023},
  eprint = {2307.08615},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.08615v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.08615.svg)](https://codeofpaper.com/paper/2307.08615)

Discussion